context7

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). This skill calls the third‑party Context7 API (e.g., https://context7.com/api/v2/context and https://context7.com/api/v2/libs/search in docs.js and search.js) and ingests returned public documentation and code snippets, so the agent reads external, potentially untrusted third‑party content.